Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update lora input linear adapter output dim. #911

Merged
merged 2 commits into from
Jan 15, 2025
Merged

Update lora input linear adapter output dim. #911

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5463e68
Update lora input linear adapter output dim.
JianyuWangV Jan 8, 2025
cfcb8fe
Update unit tests.
JianyuWangV Jan 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion axlearn/common/lora.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -501,7 +501,7 @@ def __init__(self, cfg: Config, *, parent: Module):
"adapter",
cfg.adapter.set(
input_dim=cfg.query_dim,
output_dim=cfg.query_dim,
output_dim=cfg.num_heads * cfg.per_head_dim,
num_heads=cfg.num_heads,
),
)
Expand Down
6 changes: 3 additions & 3 deletions axlearn/common/lora_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,7 +137,7 @@ def test_alpha_is_zero(self):

class LoraFusedQKVLinearTest(TestCase):
def test_forward(self):
model_dim = 6
model_dim = 16
num_heads = 2
per_head_dim = 3
seq_len = 4
Expand Down Expand Up @@ -197,7 +197,7 @@ def test_forward(self):
),
)
def test_extend_step(self, layer):
model_dim = 8
model_dim = 16
num_heads = 2
per_head_dim = 4 # change this to 4 to adapt the need of RoPE.
seq_len = 4
Expand Down Expand Up @@ -267,7 +267,7 @@ def test_extend_step(self, layer):
)

def test_prefill_states(self):
model_dim = 6
model_dim = 16
num_heads = 2
per_head_dim = 3
seq_len = 4
Expand Down
Loading